def getTweetFromRangeQuery(self):
ti = TweetInterface()
tweets = ti.rangeQuery(self._tweet_cluster['region'],
self._tweet_cluster['period'])
self._tweet_cluster['tweets'] = []
for tweet in tweets:
self._tweet_cluster['tweets'].append(tweet)
def getHistoricTweets(self, days=7): ti = TweetInterface() tweets = [] for d in xrange(1, days+1): et = int(self._tweet_cluster['period'][1]) + 24*3600*d bt = int(self._tweet_cluster['period'][0]) + 24*3600*d day_tweets = ti.rangeQuery(self._tweet_cluster['region'], [str(bt), str(et)]) for tweet in day_tweets: tweets.append(tweet) return tweets
def getHistoricTweets(self, days=7):
ti = TweetInterface()
tweets = []
for d in xrange(1, days + 1):
et = int(self._tweet_cluster['period'][1]) + 24 * 3600 * d
bt = int(self._tweet_cluster['period'][0]) + 24 * 3600 * d
day_tweets = ti.rangeQuery(self._tweet_cluster['region'],
[str(bt), str(et)])
for tweet in day_tweets:
tweets.append(tweet)
return tweets
def testWithExtendedTweets():
ti = TweetInterface(collection=TwitterConfig.extended_tweet_collection)
tweets = {}
most_popular_tweet = ''
max_retweet_count = -1
for tweet in ti.getAllFields(fields='text'):
text = tweet['text']
count = tweets.get(text, 0)
count += 1
tweets[text] = count
if count > max_retweet_count:
max_retweet_count = count
most_popular_tweet = text
print most_popular_tweet, max_retweet_count
print len(tweets)
def build_tweet_list(self):
self.tweets = [ self.tweet ]
if self.retweet:
self.tweets.append(self.retweet)
if self.quoted_tweet:
self.tweets.append(self.quoted_tweet)
self.parsed_tweets = [ TweetInterface(tweet) for tweet in self.tweets ]
def main():
ti = TweetInterface()
counts = []
x = []
now = 1381536000
interval = 24*3600
max = 0
for day in xrange(3000):
begin_time = now - (day + 1) * interval
end_time = now - day * interval
c = ti.rangeQuery(period=[begin_time, end_time], fields='_id').count()
counts.append(c)
x.append(str((12-day)%30))
if c > 0:
if c > max:
max = c
print max
def testWithTweet():
from corpus import buildAllCorpus
corpus_all = buildAllCorpus(element_type="tweets", debug=True)
for key, corpus in corpus_all.items():
break
ei = EventInterface()
ei.setDB("citybeat")
ei.setCollection("candidate_event_25by25_merged")
event = ei.getDocument()
print event
ti = TweetInterface()
cur = ti.getAllDocuments(limit=30)
tweets = []
for tweet in cur:
tweets.append(tweet)
del event["photos"]
event["tweets"] = tweets
event = BaseFeature(event, corpus=corpus)
print event.printFeatures()
def main():
ti = TweetInterface()
period = ['1354910879', '1354918838']
region = {
'min_lat': 40.73297324,
'max_lat': 40.73827852,
'min_lng': -73.99410076,
'max_lng': -73.98609447999999
}
tc = TwitterCluster()
tc.setRegion(region)
tc.setPeriod(period)
def checkTweetInRegion():
region = {}
region['min_lat'] = InstagramConfig.photo_min_lat
region['max_lat'] = InstagramConfig.photo_max_lat
region['min_lng'] = InstagramConfig.photo_min_lng
region['max_lng'] = InstagramConfig.photo_max_lng
r = Region(region)
ti = TweetInterface()
ti.setDB('citybeat_production')
ti.setCollection('tweets')
cur = ti.getAllDocuments()
tot = 0
tweet_in_region = 0
for tweet in cur:
cor = [0, 0]
cor[0] = tweet['location']['latitude']
cor[1] = tweet['location']['longitude']
tot += 1
if r.insideRegion(cor):
tweet_in_region += 1
print tweet_in_region
print tot
def main():
ti = TweetInterface()
ti.setDB('citybeat_production')
ti.setCollection('tweets')
tc = ti.getAllDocuments({'created_time' : {'$gte' : '1378711668'}})
print tc.count()
cnt = 0
for tweet in tc:
tweet = Tweet(tweet)
text = tweet.getText().lower()
if 'quinn' in text:
print text
cnt += 1
print cnt
def getTweetFromRangeQuery(self): ti = TweetInterface() tweets = ti.rangeQuery(self._tweet_cluster['region'], self._tweet_cluster['period']) self._tweet_cluster['tweets'] = [] for tweet in tweets: self._tweet_cluster['tweets'].append(tweet)